.claude/skills/schedule/SKILL.md
Schedule vault maintenance tasks using macOS launchd
npx skillsauth add DavidROliverBA/ArchitectKB .claude/skills/scheduleInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Schedule recurring vault maintenance tasks using macOS launchd (or cron on Linux).
/schedule list # List scheduled jobs
/schedule add <job> <schedule> # Add a scheduled job
/schedule remove <job> # Remove a scheduled job
/schedule run <job> # Run job immediately
/schedule status # Show job status and last run times
/schedule list
/schedule add health-check daily
/schedule add graph-rebuild hourly
/schedule add validate weekly
/schedule remove health-check
/schedule status
| Job | Description | Default Schedule |
| --------------- | ------------------------------------------------------------------ | ----------------- |
| health-check | Run vault health check (scripts/health-check.js) | Daily at 6am |
| validate | Run frontmatter/link validation (scripts/validate.js) | Weekly on Monday |
| graph-rebuild | Rebuild knowledge graph index (scripts/generate-graph-enhanced.js) | Hourly |
| vault-index | Rebuild SQLite FTS5 search index (scripts/vault-to-sqlite.js) | Daily at 5am |
| backup | Git commit and push vault changes | Daily at midnight |
| weblink-check | Check for dead weblinks | Weekly on Sunday |
| custom | User-defined command | As specified |
| Format | Description | Example |
| ------------- | -------------------------- | ------------------ |
| hourly | Every hour at :00 | hourly |
| daily | Every day at 6:00 AM | daily |
| daily@HH:MM | Every day at specific time | daily@09:30 |
| weekly | Every Monday at 6:00 AM | weekly |
| weekly@DAY | Specific day at 6:00 AM | weekly@friday |
| cron EXPR | Cron expression (5 fields) | cron 0 */4 * * * |
Identify the subcommand:
list - Show all scheduled jobsadd - Create new scheduled jobremove - Delete scheduled jobrun - Execute job immediatelystatus - Show job statuslist:Read launchd plist files from ~/Library/LaunchAgents/:
ls -la ~/Library/LaunchAgents/com.vault.* 2>/dev/null
Display in table format:
Scheduled Vault Jobs
====================
| Job | Schedule | Status | Last Run |
|---------------|---------------|---------|------------|
| health-check | Daily @ 06:00 | Active | 2026-01-26 |
| graph-rebuild | Hourly | Active | 2026-01-26 |
| validate | Weekly Mon | Paused | 2026-01-20 |
add:~/Library/LaunchAgents/com.vault.{{job}}.plistlaunchctl load ~/Library/LaunchAgents/com.vault.{{job}}.plistPlist Template:
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
<key>Label</key>
<string>com.vault.{{job}}</string>
<key>ProgramArguments</key>
<array>
<string>/usr/local/bin/node</string>
<string>{{vault_path}}/scripts/{{script}}.js</string>
</array>
<key>WorkingDirectory</key>
<string>{{vault_path}}</string>
<key>StartCalendarInterval</key>
{{schedule_dict}}
<key>StandardOutPath</key>
<string>{{vault_path}}/.claude/logs/{{job}}.log</string>
<key>StandardErrorPath</key>
<string>{{vault_path}}/.claude/logs/{{job}}.error.log</string>
<key>EnvironmentVariables</key>
<dict>
<key>PATH</key>
<string>/usr/local/bin:/usr/bin:/bin</string>
</dict>
</dict>
</plist>
Schedule Dict Examples:
<!-- Daily at 6am -->
<dict>
<key>Hour</key>
<integer>6</integer>
<key>Minute</key>
<integer>0</integer>
</dict>
<!-- Hourly -->
<dict>
<key>Minute</key>
<integer>0</integer>
</dict>
<!-- Weekly on Monday -->
<dict>
<key>Weekday</key>
<integer>1</integer>
<key>Hour</key>
<integer>6</integer>
<key>Minute</key>
<integer>0</integer>
</dict>
remove:launchctl unload ~/Library/LaunchAgents/com.vault.{{job}}.plistrun:Execute the job immediately:
launchctl start com.vault.{{job}}
Or run directly:
node scripts/{{script}}.js
status:Show status for all jobs:
launchctl list | grep com.vault
Display last run times from log files.
Map job names to scripts:
const JOBS = {
"health-check": {
script: "health-check.js",
defaultSchedule: "daily",
description: "Run vault health check",
},
validate: {
script: "validate.js",
defaultSchedule: "weekly",
description: "Validate frontmatter and links",
},
"graph-rebuild": {
script: "generate-graph-enhanced.js",
defaultSchedule: "hourly",
description: "Rebuild knowledge graph index",
},
"vault-index": {
script: "vault-to-sqlite.js",
defaultSchedule: "daily@05:00",
description: "Rebuild SQLite FTS5 search index",
},
backup: {
script: "backup.sh",
defaultSchedule: "daily@00:00",
description: "Git commit and push",
},
"weblink-check": {
script: "check-weblinks.js",
defaultSchedule: "weekly@sunday",
description: "Check for dead weblinks",
},
};
Ensure log directory exists:
mkdir -p .claude/logs
Create backup script if not exists (.claude/scripts/backup.sh):
#!/bin/bash
cd "$(dirname "$0")/../.."
git add -A
git commit -m "Automated backup: $(date +%Y-%m-%d)"
git push origin main
For Linux systems, use crontab instead:
# Add to crontab
(crontab -l 2>/dev/null; echo "0 6 * * * cd {{vault_path}} && node scripts/health-check.js") | crontab -
# List crontab
crontab -l | grep vault
# Remove from crontab
crontab -l | grep -v "{{job}}" | crontab -
After any operation, display:
Schedule Operation Complete
===========================
Action: {{action}}
Job: {{job}}
Status: {{success/failed}}
{{details}}
Next run: {{next_scheduled_time}}
Log file: .claude/logs/{{job}}.log
tools
--- context: fork --- # /youtube Save a YouTube video as both a Weblink (quick reference) and a detailed Page (full analysis). ## Usage ``` /youtube <url> /youtube <url> <optional title override> ``` ## Examples ``` /youtube https://www.youtube.com/watch?v=0TpON5T-Sw4 /youtube https://youtu.be/abc123 AWS re:Invent Keynote ``` ## Prerequisites This skill uses the MCP Docker YouTube tools: - `mcp__MCP_DOCKER__get_video_info` - Video metadata - `mcp__MCP_DOCKER__get_transcript` - Full trans
data-ai
Create and manage git worktrees for parallel agent sessions
testing
--- context: fork --- # /wipe Generate a context handoff summary, clear the session, and resume in a fresh conversation. Detects environment and provides automated (tmux) or manual workflow. ## Usage ``` /wipe /wipe quick # Minimal handoff, just essentials /wipe detailed # Comprehensive handoff with full context ``` ## Instructions When the user invokes `/wipe`: ### Phase 1: Detect Environment First, check the terminal environment: ```bash echo "Environment Detection:"
data-ai
--- context: fork --- # /weekly-summary Generate comprehensive weekly summary from daily notes, meetings, tasks, and project updates using parallel sub-agents. ## Usage ``` /weekly-summary /weekly-summary --last-week /weekly-summary --from 2026-01-01 --to 2026-01-07 /weekly-summary --output page # Create Page note instead of just outputting ``` ## Instructions This skill uses **5 parallel sub-agents** to gather data concurrently from different vault areas, then synthesizes a comprehensi